Journal of NeuroEngineering and Rehabilitation最新文献

{"title":"Identification of needs for an assistive robotic arm in individuals with tetraplegia: a mixed-methods approach.","authors":"N Hutmacher, A Bellwald, R Rätz, G Gruener, P Eichelberger, N Lutz, V Steiner, A M Raab","doi":"10.1186/s12984-025-01642-8","DOIUrl":"10.1186/s12984-025-01642-8","url":null,"abstract":"<p><strong>Background: </strong>A severe spinal cord injury (SCI) can profoundly affect an individual's physical abilities and social independence. For individuals living with tetraplegia, an assistive robotic arm offers the potential to restore some autonomy and reduce the need for constant assistance. However, current assistive technologies are often costly, impractical, and fail to meet the needs of those affected. This leads to high rates of abandonment and user frustration with the technology. The aim of this study was to identify the needs and expectations of both individuals with tetraplegia and their caregivers regarding an assistive robotic arm in performing everyday activities.</p><p><strong>Methods: </strong>A mixed-method approach was used, beginning with a focus group interview and followed by two online surveys; one aimed at individuals with tetraplegia and the other at caregivers. Qualitative analysis of the focus groups was performed using Focus Group Illustration Mapping. The online surveys were analyzed descriptively and qualitatively using structured content analysis.</p><p><strong>Results: </strong>A total of seven participants (individuals with tetraplegia, caregivers, physiotherapists, and an engineer) took part in the focus group interview. The online surveys were completed by 49 individuals with tetraplegia and nine caregivers. The results showed that the participants were open to using a robotic arm but none used one at the time of reporting. The participants reported that a robotic arm should assist in unilateral activities such as reaching, grasping, handling objects and body manipulation. The greatest need was reported for functions related to object manipulation and for contact with the person's body. The participants reported wanting control over the robotic arm via voice commands or with a joystick. Concerns were reported regarding costs, the weight and the space required for the robotic arm.</p><p><strong>Conclusions: </strong>In our study, individuals with tetraplegia reported that they would use assistive robotic arms for activities related to reaching, grasping, and object manipulation. Concerns regarding costs, weight and space requirements were reported. Our findings provide insights from a user perspective, informing future technical developments relevant to the tetraplegic population. However, generalizability might be reduced.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"113"},"PeriodicalIF":5.2,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12093749/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144110783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing lower-limb rehabilitation: a scoping review of augmented reality environment.","authors":"Yuanyuan Liu, Qiong Zhang, Weiyi Li","doi":"10.1186/s12984-025-01643-7","DOIUrl":"10.1186/s12984-025-01643-7","url":null,"abstract":"<p><strong>Background: </strong>Lower-limb rehabilitation is crucial for restoring motor function in individuals with physical impairments; however, traditional rehabilitation approaches often encounter challenges such as limited resources and reduced patient motivation. Augmented reality (AR) offers an innovative approach by enriching rehabilitation with interactive and engaging experiences, thereby enhancing both motivation and treatment outcomes. AR environments enable patients to practice exercises in an immersive setting that emulates real-life scenarios, potentially increasing adherence and improving functional recovery.</p><p><strong>Methods: </strong>This scoping review analyzed 25 peer-reviewed studies on the use of AR within the \"Environment\" component of the Human-Computer-Environment system for lower-limb rehabilitation. We present a taxonomy of existing AR systems, categorizing them by rehabilitation tasks (content) and interaction modes (form), which identify both physical and virtual elements that contribute to a supportive AR environment.</p><p><strong>Discussion: </strong>The findings suggest that well-designed AR environments offer a flexible and cost-effective approach to various rehabilitation tasks. Customization is essential for addressing specific rehabilitation stages, including muscle strengthening, balance improvement, and gait training. The integration of multisensory feedback, such as visual, auditory, and haptic cues, enhances patient engagement and provides real-time performance monitoring. Effective AR environments must also account for the distinct needs of each limb, particularly for bilateral impairments, and ensure sufficient space for safe movement. By providing an individualized rehabilitation experience, AR environments have the potential to significantly improve patient motivation and outcomes. Future research should explore the integration of AR environments with assistive technologies, such as wearable devices and exoskeletons, to further enhance rehabilitation possibilities.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"114"},"PeriodicalIF":5.2,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12093737/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144110777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Neuromusculoskeletal Modeling Pipeline: MATLAB-based model personalization and treatment optimization functionality for OpenSim.","authors":"Claire V Hammond, Spencer T Williams, Marleny M Vega, Di Ao, Geng Li, Robert M Salati, Kayla M Pariser, Mohammad S Shourijeh, Ayman W Habib, Carolynn Patten, Benjamin J Fregly","doi":"10.1186/s12984-025-01629-5","DOIUrl":"10.1186/s12984-025-01629-5","url":null,"abstract":"<p><p>Neuromusculoskeletal injuries including osteoarthritis, stroke, spinal cord injury, and traumatic brain injury affect roughly 19% of the U.S. adult population. Standardized interventions have produced suboptimal functional outcomes due to the unique treatment needs of each patient. Strides have been made to utilize computational models to develop personalized treatments, but researchers and clinicians have yet to cross the \"valley of death\" between fundamental research and clinical usefulness. This article introduces the Neuromusculoskeletal Modeling (NMSM) Pipeline, two MATLAB-based toolsets that add Model Personalization and Treatment Optimization functionality to OpenSim. The two toolsets facilitate computational design of individualized treatments for neuromusculoskeletal impairments through the use of personalized neuromusculoskeletal models and predictive simulation. The Model Personalization toolset contains four tools for personalizing 1) joint structure models, 2) muscle-tendon models, 3) neural control models, and 4) foot-ground contact models. The Treatment Optimization toolset contains three tools for predicting and optimizing a patient's functional outcome for different treatment options using a patient's personalized neuromusculoskeletal model and direct collocation optimal control methods. Support for user-defined cost, constraint, and model modification functions facilitate simulation of a vast number of possible treatments. An NMSM Pipeline use case is presented for an individual post-stroke with impaired walking function, where the goal was to predict how the subject's neural control could be changed to improve walking speed without increasing metabolic cost. First the Model Personalization toolset was used to develop a personalized neuromusculoskeletal model of the subject starting from a generic OpenSim full-body model and experimental walking data (video motion capture, ground reaction, and electromyography) collected from the subject at his self-selected speed. Next the Treatment Optimization toolset was used with the personalized model to predict how the subject could recruit existing muscle synergies more effectively to reduce muscle activation disparities between the paretic and non-paretic legs. The software predicted that the subject could increase his walking speed by 60% without increasing his metabolic cost per unit time by modifying existing muscle synergy recruitment. This hypothetical treatment demonstrates how NMSM Pipeline tools could allow researchers working collaboratively with clinicians to develop personalized neuromusculoskeletal models of individual patients and to perform predictive simulations for designing personalized treatments that maximize a patient's post-treatment functional outcome.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"112"},"PeriodicalIF":5.2,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12087055/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144094010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Safety and effectiveness of non-invasive brain stimulation on mobility and balance function in children with cerebral palsy: a systematic review and meta-analysis.","authors":"Mengru Zhong, Yage Zhang, Jie Luo, Tingting Chen, Jingbo Zhang, Tingting Peng, Mingshan Han, Wen Le, Tingting Peng, Kaishou Xu","doi":"10.1186/s12984-025-01619-7","DOIUrl":"10.1186/s12984-025-01619-7","url":null,"abstract":"<p><strong>Background: </strong>Children with cerebral palsy (CP) experience significant mobility and balance impairments. Non-invasive brain stimulation (NIBS), including transcranial direct current stimulation (tDCS) and repetitive transcranial magnetic stimulation (rTMS), has emerged as a potential therapeutic intervention. Nevertheless, the safety and effectiveness of NIBS in children with CP remain uncertain and require further investigation. This study aimed to evaluate the safety and effectiveness of NIBS in improving mobility and balance function in children with CP.</p><p><strong>Methods: </strong>Randomized controlled trials written in English were searched in five databases (PubMed, Embase, Scopus, Web of Science, and ProQuest), from the first available records in each database to April 2024. Statistical analysis focused on outcomes related to mobility and balance function immediately following intervention and one-month follow-up.</p><p><strong>Results: </strong>A total of 16 studies encompassing 346 children with CP, aged 3-14 years, were included. The meta-analysis indicated that NIBS is safe and well-tolerated [Risk Difference = 0.16, 95% CI - 0.01-0.33], with a low incidence of adverse events. Significant improvements were observed in mobility post-intervention and at one-month follow-up, particularly in Gross Motor Function Measure scores [standard mean difference (SMD) = 0.47 to 0.63, P < 0.05]. Gait parameters, including gait velocity (SMD = 1.28, P < 0.01) and stride length (SMD = 0.70, P = 0.01) showed immediate improvements. However, no significant improvements were found in balance post-tDCS or at follow-up.</p><p><strong>Conclusions: </strong>Our findings support the use of NIBS as a safe and feasible tool for enhancing mobility in children with CP, demonstrating both immediate and sustained improvements in gait parameters such as velocity and stride length. However, the impact on balance remains inconclusive. Future research should focus on extending follow-up periods, increasing sample sizes, and exploring tailored stimulation protocols to better understand the long-term efficacy and optimal application of NIBS in pediatric populations.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"111"},"PeriodicalIF":5.2,"publicationDate":"2025-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12087172/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144093997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic detection of human gait events: a simple but versatile 3D algorithm.","authors":"Théo Vancanneyt, Camille Le Moal, Maxence Blard, Juliette Lenoir, Nicolas Roche, Céline Bonnyaud, Fabien Dubois","doi":"10.1186/s12984-025-01544-9","DOIUrl":"10.1186/s12984-025-01544-9","url":null,"abstract":"<p><strong>Background: </strong>Detecting Foot Strike and Foot Off events in human gait, which is cyclic yet variable, consistently requires expert correction. This subjective correction can reduce spatiotemporal parameters, joint kinematic and kinetic accuracy, regardless of the gait event detection algorithm used from the literature. Recently developed methods have combined existing algorithms to better capture this gait variability, using Ground Reaction Forces. However, those methods do not fully account for intra-individual variability, particularly in the case of multiple and simultaneous gait patterns.</p><p><strong>Method: </strong>We developed a deterministic algorithm called the Multi-Condition algorithm. This algorithm identifies the Foot Strike when the first of the foot markers loses its degrees of freedom and the Foot Off when the last of the foot markers regains its degrees of freedom.</p><p><strong>Results: </strong>This algorithm was tested on 819 C3D gait files from 9 healthy individuals and 50 individuals with stroke, multiple sclerosis, spinal cord injury, cerebral palsy, polio, neuromuscular disease or amputation. The Multi-Condition algorithm detected both Foot Strike and Foot Off within a range of three frames, which was more accurate and precise than the inter-rater variability of expert correction. Detection of gait events required only a few seconds, regardless of the pathology or gait pattern, even when considering intra-individual variability.</p><p><strong>Conclusion: </strong>Accurately identifying gait events is the first critical step in providing reliable gait analysis parameters for clinicians. The Multi-Condition algorithm aims to achieve deterministic consensus in the accurate and precise identification of gait events, regardless of the pathology or the gait pattern. To promote its adoption and ongoing testing, the Multi-Condition algorithm is available as an open-access resource.</p><p><strong>Ethical committee: </strong>The study was approved by the University of Paris-Saclay Research Ethics Committee (No. CER-Paris-Saclay-2024-35) and was performed in accordance with the Declaration of Helsinki.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"110"},"PeriodicalIF":5.2,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12077026/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144011642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hidden Markov model-based similarity measure (HMM-SM) for gait quality assessment of lower-limb prosthetic users using inertial sensor signals.","authors":"Gabriel Ng, Jan Andrysek","doi":"10.1186/s12984-025-01638-4","DOIUrl":"10.1186/s12984-025-01638-4","url":null,"abstract":"<p><strong>Background: </strong>Gait quality indices, such as the Gillette Gait Index or Gait Profile Score (GPS), can provide clinicians with objective, straightforward measures to quantify gait pathology and monitor changes over time. However, these methods often require motion capture or stationary gait analysis systems, limiting their accessibility. Inertial sensors offer a portable, cost-effective alternative for gait analysis. This study aimed to evaluate a novel hidden Markov model-based similarity measure (HMM-SM) for assessing gait quality directly from gyroscope and accelerometer data captured by inertial sensors.</p><p><strong>Methods: </strong>Walking trials were conducted with 26 lower-limb prosthetic users and 30 able-bodied individuals, using inertial sensors placed at various lower body locations. We computed the HMM-SM score along with other established inertial sensor-based methods, including the Movement Deviation Profile, Dynamic Time Warping, IMU-based Gait Normalcy Index, and Multifeature Gait Score. Spearman correlations with the GPS, a validated measure of gait quality, were assessed, as well as correlations among the inertial sensor methods. Welch's t-tests were used to evaluate the ability to distinguish between prosthetic subgroups.</p><p><strong>Results: </strong>The HMM-SM and other inertial sensor-based methods demonstrated moderate-to-strong correlations with the GPS (0.49 <|r|< 0.77 for significant correlations). Comparisons between different measures highlighted key similarities and differences, both in correlations and in their ability to differentiate between subgroups. Overall, the pelvis and lower leg sensors achieved significant correlations and outperformed the upper leg sensors, which did not achieve significant correlations with the GPS for any of the signal-based measures.</p><p><strong>Conclusion: </strong>Results suggest inertial sensors located at the pelvis and lower leg provide valid markers for monitoring overall gait quality, offering the potential to develop nonobtrusive, wearable systems to facilitate long-term monitoring. Such systems could enhance rehabilitation by enabling continuous gait assessment that can be easily integrated in clinical and everyday settings.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"109"},"PeriodicalIF":5.2,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12070658/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144025574","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing the dynamic treatment regime of outpatient rehabilitation in patients with knee osteoarthritis using reinforcement learning.","authors":"Sijia Liu, Jiawei Luo, Chengqi He","doi":"10.1186/s12984-025-01609-9","DOIUrl":"https://doi.org/10.1186/s12984-025-01609-9","url":null,"abstract":"<p><strong>Background: </strong>Knee osteoarthritis (KOA) is a prevalent chronic disease worldwide, and traditional treatment methods lack personalized adjustment for individual patient differences and cannot meet the needs of personalized treatment.</p><p><strong>Methods: </strong>In this study, a dedicated knee osteoarthritis bank (KOADB) was constructed by collecting extensive clinical data from patients. Random forest was used to select the features that had the greatest impact on treatment decisions from 122 questionnaire items. The questionnaire design was optimized to reduce the burden on patients and ensure the validity of data collection. Then, based on the key features screened out, a dynamic treatment recommendation system was constructed by using deep reinforcement learning algorithms, including Deep Deterministic Policy Gradien(DDPG), Deep Q-Network(DQN) and Batch-Constrained Q-learning(BCQ). A large number of simulation experiments have verified the effectiveness of these algorithms in optimizing the treatment strategy of KOA. Finally, the applicability and accuracy of the model were evaluated by comparing the treatment behaviors with actual patients.</p><p><strong>Results: </strong>In the application of deep reinforcement learning algorithms to treatment optimization, the BCQ algorithm achieves the highest success rate (79.1%), outperforming both DQN (68.1%) and DDPG (76.2%). These algorithms significantly outperform the treatment strategies that patients actually receive, demonstrating their advantages in dealing with dynamic and complex decisions.</p><p><strong>Conclusions: </strong>In this study, a deep learning-based KOA treatment optimization model was developed, which was able to adjust the treatment plan in real time and respond to changes in patient status. By integrating feature selection and reinforcement learning techniques, this study proposes an innovative method for treatment optimization, which offers new possibilities for chronic disease management and demonstrates certain feasibility in the development of personalized medicine and precision treatment strategies.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"107"},"PeriodicalIF":5.2,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12060546/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143996752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gait speed-dependent modulation of paretic versus non-paretic propulsion in persons with chronic stroke.","authors":"Joost Biere, Brenda E Groen, Carmen J Ensink, Jorik Nonnekes, Noël L W Keijsers","doi":"10.1186/s12984-025-01620-0","DOIUrl":"https://doi.org/10.1186/s12984-025-01620-0","url":null,"abstract":"<p><strong>Background: </strong>Persons with chronic stroke (PwCS) exhibit impaired paretic propulsion generation. Consequently, PwCS walk slower than healthy peers and rely more on their non-paretic leg, leading to propulsion asymmetry. However, it remains unclear how propulsion symmetry is influenced by walking at various gait speeds. This study aimed to investigate the relation between gait speed and propulsion symmetry in PwCS and controls.</p><p><strong>Methods: </strong>Fifteen PwCS and sixteen healthy controls walked on an instrumented treadmill at randomized speeds, ranging from 0.2 m/s to comfortable walking speeds for PwCS or 0.4 to 1.6 m/s for controls, with 0.2 m/s increments. PwCS continued to their maximum speed with 0.1 m/s increments. Propulsion, derived from the anteroposterior component of the ground reaction force, was defined as propulsion peak and propulsion impulse. The primary outcome was propulsion peak and impulse symmetry (paretic propulsion / total propulsion), with secondary outcomes being propulsion peak and impulse per leg. The relationship between gait speed and propulsion metrics was analyzed using linear mixed models (LMM).</p><p><strong>Results: </strong>PwCS exhibited clear propulsion peak and impulse asymmetry across all gait speeds, while controls maintained symmetrical propulsion. LMMs revealed no change in propulsion peak symmetry with gait speed (β = 0.12, SE = 0.090, p = 0.19), with considerable variability among PwCS. Propulsion impulse symmetry improved with increasing gait speed (β = 0.39, SE = 0.048, p < 0.001), especially in PwCS who had greater asymmetry at comfortable walking speed. Propulsion peak and impulse increased with gait speed in both legs for PwCS and controls. The propulsion peak increase was stronger in the non-paretic compared to the paretic leg (0.16 ± 0.043 vs. 0.12 ± 0.042 N/kg per 0.1 m/s), while the propulsion impulse increase was similar between legs.</p><p><strong>Conclusions: </strong>PwCS showed reduced paretic leg contribution to forward propulsion across various gait speeds. The relative paretic contribution for propulsion peak remained constant while it increased with gait speed for propulsion impulse, especially in those with greater asymmetry at their comfortable walking speed. Furthermore, all participants were able to increase paretic propulsion peak and impulse above their propulsion at comfortable walking speed, suggesting some residual paretic capacity.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"108"},"PeriodicalIF":5.2,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12063273/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144024464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multi-label deep residual shrinkage network for high-density surface electromyography decomposition in real-time.","authors":"Jinting Ma, Lifen Wang, Renxiang Wu, Naiwen Zhang, Jing Wei, Jianjun Li, Qiuyuan Li, Lihai Tan, Guanglin Li, Naifu Jiang, Guo Dan","doi":"10.1186/s12984-025-01639-3","DOIUrl":"https://doi.org/10.1186/s12984-025-01639-3","url":null,"abstract":"<p><strong>Background: </strong>The swift and accurate identification of motor unit spike trains (MUSTs) from surface electromyography (sEMG) is essential for enabling real-time control in neural interfaces. However, the existing sEMG decomposition methods, including blind source separation (BSS) and deep learning, have not yet achieved satisfactory performance, due to high latency or low accuracy.</p><p><strong>Methods: </strong>This study introduces a novel real-time high-density sEMG (HD-sEMG) decomposition algorithm named ML-DRSNet, which combines multi-label learning with a deep residual shrinkage network (DRSNet) to improve accuracy and reduce latency. ML-DRSNet was evaluated on a public sEMG dataset and the corresponding MUSTs extracted via the convolutional BSS algorithm. An improved multi-label deep convolutional neural network (ML-DCNN) was also evaluated and compared against a conventional multi-task DCNN (MT-DCNN). These networks were trained and tested on various window sizes and step sizes.</p><p><strong>Results: </strong>With the shortest window size (20 data points) and step size (10 data points), ML-DRSNet significantly outperformed both ML-DCNN (0.86 ± 0.18 vs. 0.71 ± 0.24, P < 0.001) and MT-DCNN (0.86 ± 0.18 vs. 0.66 ± 0.16, P < 0.001) in decomposition precision. Moreover, ML-DRSNet demonstrated a notably lower latency (15.15 ms) compared to ML-DCNN (69.36 ms) and MT-DCNN (76.96 ms), both of which demonstrated reduced latency relative to BSS-based decomposition methods.</p><p><strong>Conclusions: </strong>The proposed ML-DRSNet and the improved ML-DCNN algorithms substantially enhance both the accuracy and real-time performance in decomposing MUSTs, establishing a technical foundation for neuro-information-driven motor intention recognition and disease assessment.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"106"},"PeriodicalIF":5.2,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12060341/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144017511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"User accommodation to an active microprocessor-controlled knee in individuals with unilateral transfemoral amputation: a 5-week non-randomized trial.","authors":"Elke Lathouwers, Alexandre Maricot, Bruno Tassignon, Sybille Geers, Louis Flynn, Tom Verstraten, Kevin De Pauw","doi":"10.1186/s12984-025-01637-5","DOIUrl":"https://doi.org/10.1186/s12984-025-01637-5","url":null,"abstract":"<p><strong>Background: </strong>Evaluation studies on active microprocessor-controlled knees (AMPK) in individuals with unilateral transfemoral amputation (TFA) are lacking in the literature. Furthermore, research on user accommodation to AMPK remains to be investigated. Hence, this study aims to conduct a comparison between an AMPK and individual's current prosthesis and assess the accommodation to using an AMPK during daily activities over a 5-week period on functional performance tests.</p><p><strong>Methods: </strong>Participants with TFA completed a protocol comprising L-test, slope walking, level walking (2MWT) and dual-task level walking (dual-2MWT) once a week with their current prosthesis and the AMPK. The outcomes of interest were the distance covered during the 2MWT and dual-2MWT, time required to perform the L-test, accuracy of the serial subtractions during the dual-2MWT, heart rate (HR), rating of perceived exertion, fatigue, comfort and perceived workload. Generalised least-squared models were built to investigate differences in prosthetic conditions over time. Pearson correlations were calculated to determine associations between the performance and subjective outcomes. The level of significance was set at 0.05.</p><p><strong>Results: </strong>Seven participants (age = 53 years ± 14 years) completed the study. Over time, the AMPK participants took longer to complete the L-test than their current prosthesis (p < 0.001). They reported higher fatigue (p = 0.033), lower comfort (p = 0.010), and higher perceived exertion with the AMPK (p = 0.048). Slope walking showed no significant walking speed or HR differences except higher HR with the AMPK in session 3 (p = 0.032). Dual-task level walking demonstrated lower walking speed with the AMPK (p = 0.035) and more responses to serial subtractions in sessions two (p = 0.043) and four (p = 0.023). No other differences between conditions were found on one of the functional tests. Weak associations (|r|= 0-0.5) were observed between performance and subjective measures.</p><p><strong>Conclusion: </strong>Using the AMPK highlights initial challenges in task completion times and subjective comfort and fatigue levels. Our findings indicate that five one-hour sessions are insufficient for achieving user accommodation, and underscore the need for further research with a larger sample, continued prosthetic use and user accommodation to enhance prosthetic functioning and user experiences.</p><p><strong>Trial registration: </strong>NCT05407545.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"105"},"PeriodicalIF":5.2,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12057274/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144011723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}